Framework for investigating the current–voltage topographies prediction model of quantum-confined metallic gate enclosed biomolecular nanoribbon based on DFT and machine learning

100. Availability and reporting quality of external validations of ML prediction models with orthopedic surgical outcomes: A systematic review

Risk of intraoperative hemorrhage during cesarean scar ectopic pregnancy surgery: development and validation of an interpretable machine learning prediction model

Background and purpose — External validation of machine learning (ML) prediction models is an essential step before clinical application. We assessed the proportion, performance, and transparent reporting of externally validated ML prediction models in orthopedic surgery, using the Transparent Reporting for Individual Prognosis or Diagnosis (TRIPOD) guidelines. Material and methods — We performed a systematic search using synonyms for every orthopedic specialty, ML, and external validation. The proportion was determined by using 59 ML prediction models with only internal validation in orthopedic surgical outcome published up until June 18, 2020, previously identified by our group. Model performance was evaluated using discrimination, calibration, and decision-curve analysis. The TRIPOD guidelines assessed transparent reporting. Results — We included 18 studies externally validating 10 different ML prediction models of the 59 available ML models after screening 4,682 studies. All external validations identified in this review retained good discrimination. Other key performance measures were provided in only 3 studies, rendering overall performance evaluation difficult. The overall median TRIPOD completeness was 61% (IQR 43–89), with 6 items being reported in less than 4/18 of the studies. Interpretation — Most current predictive ML models are not externally validated. The 18 available external validation studies were characterized by incomplete reporting of performance measures, limiting a transparent examination of model performance. Further prospective studies are needed to validate or refute the myriad of predictive ML models in orthopedics while adhering to existing guidelines. This ensures clinicians can take full advantage of validated and clinically implementable ML decision tools.

Construction and comparison of short-term prognosis prediction model based on machine learning in acute ischemic stroke

Development and validation of a machine learning model to predict venous thromboembolism among hospitalized cancer patients

PurposeThis study aimed to use traditional statistics and machine learning to develop and validate prediction models for predicting hospital death in patients with AMI and compare these models’ performance.Patients and MethodsData were retrieved from the Medical Information Mart for Intensive Care (MIMIC III) electronic clinical database. A total of 338 eligible AMI patients were divided into a training cohort (n = 238) and a validation cohort (n = 100), and all patients were divided into survival groups and nonsurvival groups according to patients’ hospital outcomes. The performance of the traditional statistics prediction model and the optimal machine learning prediction model was evaluated and compared with respect to discrimination, calibration, and clinical utility in the validation cohort.ResultsUnivariate and multivariate logistic regression analyses identified the following independent risk factors associated with hospital death for AMI in the training cohort, including diastolic blood pressure, blood lactate, blood creatinine, age, blood pH, and red blood cell distribution width. Both the nomogram (AUC = 77.0%, 67.9–86.1%) and optimal machine learning model (AUC = 82.9%, 74.9–91.0%) achieved good discrimination and calibration in the validation cohort. Decision curves analysis showed that the optimal machine learning model has a greater net benefit than that of nomogram in this study.ConclusionThe nomogram achieved a concise and relatively accurate prediction of hospital death in patients with AMI, the machine learning model also has good discrimination and seems to have better clinical utility. Traditional statistics may help infer the relationship between risk factors and hospital death, while machine learning may contribute to a more accurate prediction. Traditional statistics and machine learning are complementary in developing the prediction model for hospital death of AMI. Therefore, a combination of nomogram–machine learning (Nomo-ML) predictive model may improve care and help clinicians make AMI management-related decisions.

BackgroundThis study aimed to develop predictive models based on preoperative clinicopathological and imaging features to accurately assess the individual risk of contralateral occult thyroid carcinoma (OTC) and determine the number of central lymph node metastasis (CLNM) in patients with unilateral papillary thyroid carcinoma, thereby providing actionable guidance for surgical planning.MethodsSeven widely-used machine learning algorithms were employed to develop predictive models. Hyperparameter tuning was performed via cross-validation in combination with grid search. The models were subsequently trained and evaluated by using the optimal hyperparameter combinations. To facilitate comparative analysis, ROC curves, calibration curves were generated and DCA was performed. The optimal model was then selected on the basis of this comprehensive evaluation. Furthermore, a clinical prediction model was constructed utilizing the significant predictors identified.ResultsThe logistic regression model was identified to be the optimal predictive model. For the clinical prediction model of OTC, the following independent variables were incorporated: body mass index, and ultrasonographic findings, including capsular disruption, number of malignant nodules within a unilateral lobe, sum of the longest diameter (SLD) of tumors, and the presence of isthmic malignant nodule(s). This model yielded an area under the ROC curve (AUC) of 0.74 and 0.70 in the training and validation cohorts, respectively. For the clinical prediction model of ≥5 CLNM, the incorporated independent variables included: age, sex, chronic lymphocytic thyroiditis, and ultrasonographic features covering malignant nodules located near the isthmus, SLD, capsular disruption, and calcification. This model produced an AUC of 0.75 and 0.71 in the training and validation cohorts, respectively. Decision curve analysis indicated that clinical interventions guided by the two models could provide net benefit within threshold probability ranges of 10% to 90% and 10% to 70% for patients with PTC. And the calibration curves demonstrated a good agreement between model predictions and actual observations.ConclusionThis study developed and validated clinical prediction models to estimate the risk of contralateral OTC and the presence of ≥5 CLNM in patients with unilateral PTC. These models were designed to prevent overtreatment in low-risk patients while providing evidence-based guidance for decision-making about treatment choice in high-risk patients.

Mineral prospectivity mapping based on Support vector machine and Random Forest algorithm – A case study from Ashele copper–zinc deposit, Xinjiang, NW China

Icing on transmission lines may cause damage to tower components and even lead to structural failure. Aiming at the lack of research on predicting mechanical characteristic parameters of weak components of transmission towers, and the cumbersome steps of building a finite element model (FEM), the study of prediction for mechanical characteristic parameters of weak components of towers based on a finite element simulation and machine learning is proposed. Firstly, a 110 kV transmission tower in a heavily iced area is taken as an example to establish its FEM. The locations of the weak components are analyzed, and the accuracy of FEM is verified. Secondly, meteorological and terrain parameters are considered as input parameters of the prediction model. The axial stresses and nodal displacements of four weak components are selected as output parameters. The FEM of the 110 kV transmission tower is used to obtain input and output datasets. Thirdly, five machine learning algorithms are considered to establish the prediction models for mechanical characteristic parameters of weak components, and the optimal prediction model is obtained. Finally, the accuracy of the prediction method is verified through an actual tower collapse case. The results show that ACO-BPNN is the optimal model that can accurately and quickly predict the mechanical characteristic parameters of the weak components of the transmission tower. This study can provide an early warning for the failure prediction of transmission towers in heavily iced areas, thus providing an important reference for their safe operation and maintenance.

Oversampling-based prediction of environmental complaints related to construction projects with imbalanced empirical-data learning

With the advances in technology and data science, machine learning (ML) is being rapidly adopted by the health care sector. However, there is a lack of literature addressing the health conditions targeted by the ML prediction models within primary health care (PHC) to date. To fill this gap in knowledge, we conducted a systematic review following the PRISMA guidelines to identify health conditions targeted by ML in PHC. We searched the Cochrane Library, Web of Science, PubMed, Elsevier, BioRxiv, Association of Computing Machinery (ACM), and IEEE Xplore databases for studies published from January 1990 to January 2022. We included primary studies addressing ML diagnostic or prognostic predictive models that were supplied completely or partially by real-world PHC data. Studies selection, data extraction, and risk of bias assessment using the prediction model study risk of bias assessment tool were performed by two investigators. Health conditions were categorized according to international classification of diseases (ICD-10). Extracted data were analyzed quantitatively. We identified 106 studies investigating 42 health conditions. These studies included 207 ML prediction models supplied by the PHC data of 24.2 million participants from 19 countries. We found that 92.4% of the studies were retrospective and 77.3% of the studies reported diagnostic predictive ML models. A majority (76.4%) of all the studies were for models' development without conducting external validation. Risk of bias assessment revealed that 90.8% of the studies were of high or unclear risk of bias. The most frequently reported health conditions were diabetes mellitus (19.8%) and Alzheimer's disease (11.3%). Our study provides a summary on the presently available ML prediction models within PHC. We draw the attention of digital health policy makers, ML models developer, and health care professionals for more future interdisciplinary research collaboration in this regard.

Spatial prediction of soil sand content at various sampling density based on geostatistical and machine learning algorithms in plain areas

This study aimed to identify the risk factors associated with spontaneous rupture and bleeding in hepatocellular carcinoma, establish a prediction model for spontaneous rupture bleeding via a machine learning algorithm, and validate and evaluate the predictive efficacy of the model. A retrospective analysis of 4209 patients with hepatocellular carcinoma (HCC) diagnosed at the Second Affiliated Hospital of Nanchang University from April 2019 to November 2023 was performed. Spontaneous rupture and bleeding occurred in 269 (6.4%) of these patients, and the clinical data of 146 patients (case group) were ultimately included, whereas the data of 144 patients without ruptured HCC (control group) were randomly chosen by matching for age, sex, and time of admission from the patients who visited our hospital during the same period. A randomly generated 70% (n = 203) was used as the training set, and the remaining 30% (n = 87) was used as the validation set. They constructed a predictive model for spontaneous rupture bleeding of hepatocellular carcinoma via 10 machine learning methods: Logistic, GBM, Neural Network, Random Forest, AdaBoost, LightGBM, CatBoost, XgBoost, KNN, and SVM models. The optimal model was screened on the basis of the area under the curve (AUC), calibration curves and confusion matrix to assess and compare the predictive performance of the models, the model was interpreted through SHAP plots, and a web-based version of the risk assessment tool for spontaneous rupture and bleeding in hepatocellular carcinoma patients was developed on the basis of the optimal machine learning predictive model. A total of 290 patients with HCC (254 males and 36 females) were included in this study. Analysis revealed that cirrhosis, neutrophil percentage, albumin levels, tumor diameter, and the presence of ascites were key predictors of spontaneous bleeding due to rupture in hepatocellular carcinoma patients. The 290 patients were randomized at a 7:3 ratio, and the training set of 203 patients and the validation set of 87 patients were simultaneously subjected to the construction of the risk prediction model. In the training set, the AUCs of the Logistic, GBM, Neural Network, Random Forest, AdaBoost, LightGBM, CatBoost, XgBoost, KNN, and SVM models are 0.911, 0.956, 0.929, 1.000, 0.919, 0.997, 0.948, 0.927, 0.984, and 0.903, respectively; in the validation set, the AUCs of the Logistic, GBM, Neural Network, Random Forest, AdaBoost, LightGBM, CatBoost, XgBoost, KNN, and SVM models are 0.940, 0.928, 0.939, 0.838, 0.897, 0.855, 0.925, 0.922, 0.888, and 0.946, respectively; among the 10 models, the SVM model has the best predictive performance. On the basis of the results of this study, a predictive model for spontaneous bleeding in hepatocellular carcinoma was presented, and a web-based version of a risk prediction assessment tool was created via SVM modeling to improve its clinical translational value.

229. Using machine learning (ML) models to predict risk of venous thromboembolism (VTE) following spine surgery

Two sets of predictive models are developed based on the machine learning (ML) and general orthogonal regression (GOR) approaches for predicting the seismic source parameters including rupture width, rupture length, rupture area, and two slip parameters (i.e., the average and maximum slips of rupture surface). The predictive models are developed based on a compiled catalog consisting of 1190 sets of estimated source parameters. First, the Light Gradient Boosting Machine (LightGBM), which is a gradient boosting framework that uses tree-based learning algorithms, is utilized to develop the ML-based predictive models by employing five predictor variables consisting of moment magnitude (Mw), hypocenter depth, dip angle, fault-type, and subduction indicators. It is found that the developed ML-based models exhibit good performance in terms of predictive efficiency and generalization. Second, multiple source-scaling models are developed for predicting the source parameters based on the GOR approach, in which each functional form has one predictor variable only, that is, Mw. The performance of the GOR-based models is compared with existing source-scaling relationships. Both sets of the models developed are applicable in estimating the five source parameters in earthquake engineering-related applications.